Search Results for author: Thomas Fang Zheng

Found 24 papers, 4 papers with code

Enhancing Quantised End-to-End ASR Models via Personalisation

no code implementations17 Sep 2023 Qiuming Zhao, Guangzhi Sun, Chao Zhang, Mingxing Xu, Thomas Fang Zheng

Recent end-to-end automatic speech recognition (ASR) models have become increasingly larger, making them particularly challenging to be deployed on resource-constrained devices.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Attack on practical speaker verification system using universal adversarial perturbations

1 code implementation19 May 2021 Weiyi Zhang, Shuning Zhao, Le Liu, Jianmin Li, Xingliang Cheng, Thomas Fang Zheng, Xiaolin Hu

In authentication scenarios, applications of practical speaker verification systems usually require a person to read a dynamic authentication text.

Real-World Adversarial Attack Room Impulse Response (RIR) +3

Squeezing value of cross-domain labels: a decoupled scoring approach for speaker verification

no code implementations27 Oct 2020 Lantian Li, Yang Zhang, Jiawen Kang, Thomas Fang Zheng, Dong Wang

Domain mismatch often occurs in real applications and causes serious performance reduction on speaker verification systems.

Speaker Verification

Deep generative factorization for speech signal

no code implementations27 Oct 2020 Haoran Sun, Lantian Li, Yunqi Cai, Yang Zhang, Thomas Fang Zheng, Dong Wang

Various information factors are blended in speech signals, which forms the primary difficulty for most speech information processing tasks.

When Automatic Voice Disguise Meets Automatic Speaker Verification

no code implementations15 Sep 2020 Linlin Zheng, Jiakang Li, Meng Sun, Xiongwei Zhang, Thomas Fang Zheng

The proposed approach generalizes well to restore the disguise with nonlinear frequency warping in VTLN by reducing its EER from 34. 3% to 18. 5%.

Miscellaneous Speaker Verification +1

Domain-Invariant Speaker Vector Projection by Model-Agnostic Meta-Learning

1 code implementation25 May 2020 Jiawen Kang, Ruiqi Liu, Lantian Li, Yunqi Cai, Dong Wang, Thomas Fang Zheng

Domain generalization remains a critical problem for speaker recognition, even with the state-of-the-art architectures based on deep neural nets.

Audio and Speech Processing

Deep factorization for speech signal

no code implementations27 Feb 2018 Lantian Li, Dong Wang, Yixiang Chen, Ying Shi, Zhiyuan Tang, Thomas Fang Zheng

Various informative factors mixed in speech signals, leading to great difficulty when decoding any of the factors.

Emotion Recognition Speaker Recognition

Full-info Training for Deep Speaker Feature Learning

no code implementations31 Oct 2017 Lantian Li, Zhiyuan Tang, Dong Wang, Thomas Fang Zheng

In recent studies, it has shown that speaker patterns can be learned from very short speech segments (e. g., 0. 3 seconds) by a carefully designed convolutional & time-delay deep neural network (CT-DNN) model.

Speaker Verification

Cross-lingual Speaker Verification with Deep Feature Learning

no code implementations22 Jun 2017 Lantian Li, Dong Wang, Askar Rozi, Thomas Fang Zheng

The experiments demonstrated that the feature-based system outperformed the i-vector system with a large margin, particularly with language mismatch between enrollment and test.

Speaker Verification

Deep Speaker Verification: Do We Need End to End?

no code implementations22 Jun 2017 Dong Wang, Lantian Li, Zhiyuan Tang, Thomas Fang Zheng

This principle has recently been applied to several prototype research on speaker verification (SV), where the feature learning and classifier are learned together with an objective function that is consistent with the evaluation metric.

Speaker Verification

Decision Making Based on Cohort Scores for Speaker Verification

no code implementations27 Sep 2016 Lantian Li, Renyu Wang, Gang Wang, Caixia Wang, Thomas Fang Zheng

In this paper, we propose a decision making approach based on multiple scores derived from a set of cohort GMMs (cohort scores).

Decision Making Speaker Verification

System Combination for Short Utterance Speaker Recognition

no code implementations31 Mar 2016 Lantian Li, Dong Wang, Xiaodong Zhang, Thomas Fang Zheng, Panshi Jin

This paper presents a combination approach to the SUSR tasks with two phonetic-aware systems: one is the DNN-based i-vector system and the other is our recently proposed subregion-based GMM-UBM system.

Speaker Recognition

Transfer Learning for Speech and Language Processing

no code implementations19 Nov 2015 Dong Wang, Thomas Fang Zheng

Transfer learning is a vital technique that generalizes models trained for one setting or task to other settings or tasks.

Multi-Task Learning speech-recognition +1

Binary Speaker Embedding

no code implementations20 Oct 2015 Lantian Li, Dong Wang, Chao Xing, Kaimin Yu, Thomas Fang Zheng

The popular i-vector model represents speakers as low-dimensional continuous vectors (i-vectors), and hence it is a way of continuous speaker embedding.

Binarization Speaker Verification

Max-margin Metric Learning for Speaker Recognition

no code implementations20 Oct 2015 Lantian Li, Dong Wang, Chao Xing, Thomas Fang Zheng

Probabilistic linear discriminant analysis (PLDA) is a popular normalization approach for the i-vector model, and has delivered state-of-the-art performance in speaker recognition.

Metric Learning Speaker Recognition

Deep Speaker Vectors for Semi Text-independent Speaker Verification

no code implementations24 May 2015 Lantian Li, Dong Wang, Zhiyong Zhang, Thomas Fang Zheng

Recent research shows that deep neural networks (DNNs) can be used to extract deep speaker vectors (d-vectors) that preserve speaker characteristics and can be used in speaker verification.

Speaker Recognition Text-Dependent Speaker Verification +2

Distant Supervision for Entity Linking

no code implementations PACLIC 2015 Miao Fan, Qiang Zhou, Thomas Fang Zheng

In this paper, we propose a new paradigm named distantly supervised entity linking (DSEL), in the sense that the disambiguated entities that belong to a huge knowledge repository (Freebase) are automatically aligned to the corresponding descriptive webpages (Wiki pages).

Descriptive Entity Linking

Probabilistic Belief Embedding for Knowledge Base Completion

no code implementations10 May 2015 Miao Fan, Qiang Zhou, Andrew Abel, Thomas Fang Zheng, Ralph Grishman

This paper contributes a novel embedding model which measures the probability of each belief $\langle h, r, t, m\rangle$ in a large-scale knowledge repository via simultaneously learning distributed representations for entities ($h$ and $t$), relations ($r$), and the words in relation mentions ($m$).

Knowledge Base Completion

Large Margin Nearest Neighbor Embedding for Knowledge Representation

no code implementations7 Apr 2015 Miao Fan, Qiang Zhou, Thomas Fang Zheng, Ralph Grishman

Traditional way of storing facts in triplets ({\it head\_entity, relation, tail\_entity}), abbreviated as ({\it h, r, t}), makes the knowledge intuitively displayed and easily acquired by mankind, but hardly computed or even reasoned by AI machines.

Link Prediction

Learning Embedding Representations for Knowledge Inference on Imperfect and Incomplete Repositories

no code implementations27 Mar 2015 Miao Fan, Qiang Zhou, Thomas Fang Zheng

This paper considers the problem of knowledge inference on large-scale imperfect repositories with incomplete coverage by means of embedding entities and relations at the first attempt.

Link Prediction

Errata: Distant Supervision for Relation Extraction with Matrix Completion

no code implementations17 Nov 2014 Miao Fan, Deli Zhao, Qiang Zhou, Zhiyuan Liu, Thomas Fang Zheng, Edward Y. Chang

The essence of distantly supervised relation extraction is that it is an incomplete multi-label classification problem with sparse and noisy features.

Classification General Classification +3

Cannot find the paper you are looking for? You can Submit a new open access paper.